scholarly journals TIG Stainless Steel Molten Pool Contour Detection and Weld Width Prediction Based on Res-Seg

Metals ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. 1495
Author(s):  
Yiming Wang ◽  
Jing Han ◽  
Jun Lu ◽  
Lianfa Bai ◽  
Zhuang Zhao
Keyword(s):  
Edge Detection ◽  
Molten Pool ◽  
Morphological Characteristics ◽  
Semantic Segmentation ◽  
Morphological Data ◽  
Generative Adversarial Networks ◽  
Pool Data ◽  
Data Set ◽  
Weld Width ◽  
Detection Algorithms

As the basic visual morphological characteristics of molten pool, contour extraction plays an important role in on-line monitoring of welding quality. The limitations of traditional edge detection algorithms make deep learning play a more important role in the task of target segmentation. In this paper, a molten pool visual sensing system in a tungsten inert gas welding (TIG) process environment is established and the corresponding molten pool image data set is made. Based on a residual network, a multi-scale feature fusion semantic segmentation network Res-Seg is designed. In order to further improve the generalization ability of the network model, this paper uses deep convolutional generative adversarial networks (DCGAN) to supplement the molten pool data set, then performs color and morphological data enhancement before network training. By comparing with other traditional edge detection algorithms and semantic segmentation network, it is verified that the scheme has high accuracy and robustness in the actual welding environment. Moreover, a back propagation (BP) neural network is used to predict the weld width, and a fitting test is carried out for the pixel width of the molten pool and its corresponding actual weld width. The average testing error is less than 0.2 mm, which meets the welding accuracy requirements.

scholarly journals Combined Multi-Layer Feature Fusion and Edge Detection Method for Distributed Photovoltaic Power Station Identification

Energies ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 6742
Author(s):  
Yongshi Jie ◽  
Xianhua Ji ◽  
Anzhi Yue ◽  
Jingbo Chen ◽  
Yupeng Deng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Edge Detection ◽  
Semantic Segmentation ◽  
Remote Sensing Images ◽  
Power Station ◽  
Data Set ◽  
Photovoltaic Panels ◽  
Power Stations ◽  
Photovoltaic Power

Distributed photovoltaic power stations are an effective way to develop and utilize solar energy resources. Using high-resolution remote sensing images to obtain the locations, distribution, and areas of distributed photovoltaic power stations over a large region is important to energy companies, government departments, and investors. In this paper, a deep convolutional neural network was used to extract distributed photovoltaic power stations from high-resolution remote sensing images automatically, accurately, and efficiently. Based on a semantic segmentation model with an encoder-decoder structure, a gated fusion module was introduced to address the problem that small photovoltaic panels are difficult to identify. Further, to solve the problems of blurred edges in the segmentation results and that adjacent photovoltaic panels can easily be adhered, this work combines an edge detection network and a semantic segmentation network for multi-task learning to extract the boundaries of photovoltaic panels in a refined manner. Comparative experiments conducted on the Duke California Solar Array data set and a self-constructed Shanghai Distributed Photovoltaic Power Station data set show that, compared with SegNet, LinkNet, UNet, and FPN, the proposed method obtained the highest identification accuracy on both data sets, and its F1-scores reached 84.79% and 94.03%, respectively. These results indicate that effectively combining multi-layer features with a gated fusion module and introducing an edge detection network to refine the segmentation improves the accuracy of distributed photovoltaic power station identification.

scholarly journals Fractional Order Processing of Satellite Images

2021 ◽  
Vol 11 (11) ◽  
pp. 5288
Author(s):  
Manuel Henriques ◽  
Duarte Valério ◽  
Rui Melicio
Keyword(s):  
Edge Detection ◽  
Fractional Order ◽  
High Performance ◽  
Satellite Images ◽  
Automatic Detection ◽  
Automatic Processing ◽  
Order Processing ◽  
Detection Algorithms ◽  
Grey Scale ◽  
Fixed Set

Nowadays, satellite images are used in many applications, and their automatic processing is vital. Conventional integer grey-scale edge detection algorithms are often used for this. This study shows that the use of color-based, fractional order edge detection may enhance the results obtained using conventional techniques in satellite images. It also shows that it is possible to find a fixed set of parameters, allowing automatic detection while maintaining high performance.

Semantic Segmentation of High Resolution Satellite Imagery using Generative Adversarial Networks with Progressive Growing

2021 ◽  
Vol 12 (5) ◽  
pp. 439-448
Author(s):  
Edward Collier ◽  
Supratik Mukhopadhyay ◽  
Kate Duffy ◽  
Sangram Ganguly ◽  
Geri Madanguit ◽  
...  
Keyword(s):  
High Resolution ◽  
Satellite Imagery ◽  
Semantic Segmentation ◽  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
High Resolution Satellite Imagery

scholarly journals A Fast and Lightweight Method with Feature Fusion and Multi-Context for Face Detection

2018 ◽  
Vol 10 (8) ◽  
pp. 80
Author(s):  
Lei Zhang ◽  
Xiaoli Zhi
Keyword(s):  
Face Detection ◽  
Graphics Processing Units ◽  
High Performance ◽  
Feature Fusion ◽  
Local Context ◽  
Data Set ◽  
Global Context ◽  
Detection Algorithms ◽  
Multi Scale ◽  
Benchmark Datasets

Convolutional neural networks (CNN for short) have made great progress in face detection. They mostly take computation intensive networks as the backbone in order to obtain high precision, and they cannot get a good detection speed without the support of high-performance GPUs (Graphics Processing Units). This limits CNN-based face detection algorithms in real applications, especially in some speed dependent ones. To alleviate this problem, we propose a lightweight face detector in this paper, which takes a fast residual network as backbone. Our method can run fast even on cheap and ordinary GPUs. To guarantee its detection precision, multi-scale features and multi-context are fully exploited in efficient ways. Specifically, feature fusion is used to obtain semantic strongly multi-scale features firstly. Then multi-context including both local and global context is added to these multi-scale features without extra computational burden. The local context is added through a depthwise separable convolution based approach, and the global context by a simple global average pooling way. Experimental results show that our method can run at about 110 fps on VGA (Video Graphics Array)-resolution images, while still maintaining competitive precision on WIDER FACE and FDDB (Face Detection Data Set and Benchmark) datasets as compared with its state-of-the-art counterparts.

Based on the CO2 Gas Shielded Welding Molten Pool Image Edge Detection Algorithm

2013 ◽  
Vol 437 ◽  
pp. 840-844 ◽  
Author(s):  
Xiao Gang Liu ◽  
Bing Zhao
Keyword(s):  
Edge Detection ◽  
Molten Pool ◽  
High Speed ◽  
Vision System ◽  
Detection Algorithm ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Low Pass ◽  
Defect Recognition ◽  
Pool Image

This paper use the passive vision system through high-speed camera collects molten pool images; and then according to the frequency domain characteristics of the weld pool image Butterworth low-pass filter; gradient method for image enhancement obtained after pretreatment. Research Roberts, Sobel, Prewitt, Log, Zerocross, and Canny 6 both traditional differential operator edge detection processing results. Through comparison and analysis of choosing threshold for [0.1, 0. Canny operator can get the ideal molten pool edge character, for subsequent welding molten pool defect recognition provides favorable conditions.

scholarly journals First bioacoustic and morphological data for the presence of Pelophylax bedriagae in Bulgaria

2018 ◽  
Vol 5 (1) ◽  
pp. 54-63
Author(s):  
Simeon Lukanov ◽  
Georgi Popgeorgiev ◽  
Nikolay Tzankov
Keyword(s):  
Morphological Characteristics ◽  
Morphological Data ◽  
Marsh Frog ◽  
Water Frog ◽  
Pelophylax Ridibundus ◽  
Mating Calls ◽  
The Town ◽  
Pelophylax Bedriagae ◽  
Made In

AbstractWater frog mating calls from two localities were studied and analyzed. Recordings were made in the summer of 2010 at the Arkutino swamp near the town of Primorsko and at the Vurbitza River near the town of Momchilgrad. A total of 154 calls were analyzed and the results suggested the presence of both the Marsh frog (Pelophylax ridibundus) and the Levant frog (Pelophylax bedriagae) in both sites, with the former being more frequent in Vurbitza River, and the latter – in Arkutino. At Vurbitza, we also captured and measured 2 specimens, which morphological characteristics differed from P. ridibundus and matched those of P. bedriagae. These are the first localities for P. bedriagae in Bulgaria.

Euphorbia mongoliensis (Euphorbiaceae), a new species from Inner Mongolia, China

Phytotaxa ◽  
2021 ◽  
Vol 501 (1) ◽  
pp. 151-161
Author(s):  
ER-HUAN ZANG ◽  
MING-XU ZHANG ◽  
WEN-LE WANG ◽  
CHUN-HONG ZHANG ◽  
MIN-HUI LI
Keyword(s):  
New Species ◽  
Geographical Distribution ◽  
Inner Mongolia ◽  
Pollen Morphology ◽  
Morphological Characteristics ◽  
Euphorbia Esula ◽  
Morphological Data ◽  
New Taxon ◽  
Flora Of China ◽  
A New Species

In May 2020, a new taxon of Euphorbia, Euphorbiaceae was collected from a dry hillside of Dongsheng District, Ordos City, Inner Mongolia. The morphological characteristics of the specimens analyzed differ from those of the known Euphorbia species from this region; therefore, we suspected this may be a new species, and we set to analyze the ITS2 sequences of some Euphorbia species. The results show that the new taxon belongs to the sect. Esula of Euphorbia subg. Esula. It is similar to Euphorbia esula (description from Flora of China) but does not belong to the same species. Concomitantly, plant morphological data and pollen morphology results show significant differences between the new taxon, E. esula and E. caesia, a finding that supports the delimitation of this new taxon, which is named Euphorbia mongoliensis in accordance with its geographical distribution.

scholarly journals Intergeneric Relationships within the Early-Diverging Angiosperm Family Nymphaeaceae Based on Chloroplast Phylogenomics

2018 ◽  
Vol 19 (12) ◽  
pp. 3780 ◽  
Author(s):  
Dingxuan He ◽  
Andrew Gichira ◽  
Zhizhong Li ◽  
John Nzei ◽  
Youhao Guo ◽  
...  
Keyword(s):  
Genome Structure ◽  
Morphological Data ◽  
Basal Angiosperm ◽  
Phylogenetic Position ◽  
Data Set ◽  
Protein Coding ◽  
Plastid Genomes ◽  
Chloroplast Genomes ◽  
Gene Data ◽  
High Degree

The order Nymphaeales, consisting of three families with a record of eight genera, has gained significant interest from botanists, probably due to its position as a basal angiosperm. The phylogenetic relationships within the order have been well studied; however, a few controversial nodes still remain in the Nymphaeaceae. The position of the Nuphar genus and the monophyly of the Nymphaeaceae family remain uncertain. This study adds to the increasing number of the completely sequenced plastid genomes of the Nymphaeales and applies a large chloroplast gene data set in reconstructing the intergeneric relationships within the Nymphaeaceae. Five complete chloroplast genomes were newly generated, including a first for the monotypic Euryale genus. Using a set of 66 protein-coding genes from the chloroplast genomes of 17 taxa, the phylogenetic position of Nuphar was determined and a monophyletic Nymphaeaceae family was obtained with convincing statistical support from both partitioned and unpartitioned data schemes. Although genomic comparative analyses revealed a high degree of synteny among the chloroplast genomes of the ancient angiosperms, key minor variations were evident, particularly in the contraction/expansion of the inverted-repeat regions and in RNA-editing events. Genome structure, and gene content and arrangement were highly conserved among the chloroplast genomes. The intergeneric relationships defined in this study are congruent with those inferred using morphological data.

Sign in / Sign up

Export Citation Format

Share Document